超越回合制游戏：通过双工模型实现实时对话
Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models
AI总结：
本文提出双工模型，通过时间分割复用策略实现实时对话，提升用户与AI交互的自然度和满意度。
摘要：
随着大型语言模型（LLMs）日益渗透日常生活，对能够模拟人类对话的实时交互需求逐渐增加。传统的回合制聊天系统由LLMs驱动，在生成响应时阻止用户与系统进行口头交互。为了克服这些限制，我们采用现有LLMs来构建双工模型，使这些LLMs能够在生成输出的同时监听用户，并动态调整自身以提供即时反馈。具体而言，我们将对话的查询和响应分成几个时间片，然后采用时间分割复用（TDM）编码解码策略来伪同时处理这些片。此外，为了使LLMs能够处理实时对话，我们构建了一个包含交替时间片的查询和响应以及覆盖典型即时交互反馈类型的微调数据集。我们的实验表明，尽管对话的查询和响应被分割成不完整的片进行处理，LLMs在标准基准上的原始性能仍能通过在我们数据集上的少量微调步骤得以保持。自动和人工评估表明，双工模型使用户与AI的交互更加自然和人性化，并显著提高了用户满意度，相比普通LLMs。我们的双工模型和数据集将被发布。
英文摘要：
As large language models (LLMs) increasingly permeate daily lives, there is a growing demand for real-time interactions that mirror human conversations. Traditional turn-based chat systems driven by LLMs prevent users from verbally interacting with the system while it is generating responses. To overcome these limitations, we adapt existing LLMs to \textit{duplex models} so that these LLMs can listen for users while generating output and dynamically adjust themselves to provide users with instant feedback. % such as in response to interruptions. Specifically, we divide the queries and responses of conversations into several time slices and then adopt a time-division-multiplexing (TDM) encoding-decoding strategy to pseudo-simultaneously process these slices. Furthermore, to make LLMs proficient enough to handle real-time conversations, we build a fine-tuning dataset consisting of alternating time slices of queries and responses as well as covering typical feedback types in instantaneous interactions. Our experiments show that although the queries and responses of conversations are segmented into incomplete slices for processing, LLMs can preserve their original performance on standard benchmarks with a few fine-tuning steps on our dataset. Automatic and human evaluation indicate that duplex models make user-AI interactions more natural and human-like, and greatly improve user satisfaction compared to vanilla LLMs. Our duplex model and dataset will be released.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
